2023 in Evaluation
Health Research Study + Technology: A Transition
Palantir Foundry has actually long contributed in accelerating the study findings of our health and life scientific research partners, aiding accomplish unprecedented understandings, simplify information accessibility, boost data usability, and facilitate innovative visualization and evaluation of information sources– all while protecting the personal privacy and safety of the support data
In 2023, Foundry sustained over 50 peer-reviewed publications in well-regarded journals, covering a varied number of topics– from health center operations, to oncological drugs, to learning techniques. The year prior, our software sustained a record number of peer-reviewed publications, which we highlighted in a previous post
Our partners’ fundamental investments in technological infrastructure during the optimal of the COVID- 19 pandemic has actually made the outstanding amount of publications feasible.
Public and business healthcare partners have proactively scaled their financial investments in information sharing and study software program beyond COVID action to build an extra thorough information structure for biomedical study. For instance, the N 3 C Enclave — which houses the information of 21 5 M clients from throughout almost 100 establishments– is being used daily by countless researchers across firms and companies. Given the complexity of accessing, organizing, and harnessing ever-expanding biomedical data, the need for similar research study sources remains to increase.
In this article, we take a closer consider some notable publications from 2023 and examine what lies ahead for software-backed research study.
Arising Innovation and the Acceleration of Scientific Research
The effect of new technologies on the scientific venture is accelerating research-based outcomes at a formerly impossible range. Emerging innovations and advanced software application are helping produce extra specific, organized, and accessible data possessions, which in turn are allowing researchers to tackle significantly complicated scientific obstacles. In particular, as a modular, interoperable, and versatile system, Foundry has been made use of to sustain a varied range of scientific research studies with special research study functions, consisting of AI-assisted rehabs identification, real-world proof generation, and more.
In 2023, the sector has actually likewise seen an exponential growth in passion around utilizing Artificial Intelligence (AI)– and in particular, generative AI and large language versions (LLM)– in the health and life scientific research domains. Alongside various other core technological developments (e.g., around information top quality and functionality), the potential for AI-enabled software to accelerate clinical research study is a lot more appealing than ever. As a business leader in AI-enabled software, Palantir has actually been at the forefront of searching for liable, protected, and reliable ways to use AI-enabled capacities to sustain our companions across industries in accomplishing their essential goals.
Over the previous year, Palantir software program assisted drive vital elements of our companions’ study and we stand all set to continue collaborating with our companions in government, sector, and civil society to deal with the most pressing difficulties in health and wellness and science ahead. In the next section, we give concrete examples of just how the power of software application can help advancement scientific research study, highlighting some crucial biomedical magazines powered by Shop in 2023
2023 Publications Powered by Palantir Foundry
Along with a variety of essential cancer and COVID treatment studies, Palantir Shop also allowed brand-new findings in the wider area of research methodology. Listed below, we highlight an example of some of one of the most impactful peer-reviewed articles published in 2023 that used Palantir Foundry to assist drive their research.
Recognizing brand-new effective drug combinations for numerous myeloma
- Publication : Cancer Letters
- Authors : Peat, T.J., Gaikwad, S.M., Dubois, W., Gyabaah-Kessie, N., Zhang, S., Gorjifard, S., Phyo, Z., Andres, M., Hughitt, V.K., Simpson, R.M., Miller, M.A., Girvin, A.T., Taylor, A., Williams, D., D’Antonio, N., Zhang, Y., Rajagopalan, A., Flietner, E., Wilson, K., Zhang, X., Shinn, P., Klumpp-Thomas, C., McKnight, C., Itkin, Z., Chen, L., Kazandijian, D., Zhang, J., Michalowski, A.M., Simmons, J.K., Keats, J., Thomas, C.J., Mock, B.A.
- Summary : Numerous myeloma (MM) is often immune to medicine treatment, calling for continued expedition to determine brand-new, reliable therapeutic combinations. In this research study, researchers used high-throughput drug screening to recognize over 1900 compounds with activity versus at the very least 25 of the 47 MM cell lines examined. From these 1900 compounds, 3 61 million mixes were assessed in silico, and pairs of substances with extremely correlated activity throughout the 47 cell lines and various devices of action were selected for further analysis. Particularly, six (6 medication mixes worked at 1 decreasing over-expression of a key protein (MYC) that is typically connected to the production of malignant cells and 2 increased expression of the p 16 healthy protein, which can assist the body reduce tumor growth. In addition, three (3 identified medication mixes boosted opportunities of survival and decreased the growth of cancer cells, in part by reducing activity of paths involved in TGFβ/ SMAD signaling, which regulate the cell life cycle. These preclinical searchings for identify possibly valuable unique drug mixes for tough to deal with numerous myeloma.
New rank-based protein classification approach to boost glioblastoma treatment
- Publication : Cancers cells
- Writers : Tasci, E., Jagasia, S., Zhuge, Y., Sproull, M., Cooley Zgela, T., Mackey, M., Camphausen, K., Krauze, A.V.
- Summary : Glioblastomas, one of the most usual sort of cancerous brain tumors, differ substantially, limiting the capacity to assess the biological aspects that drive whether glioblastomas will certainly react to treatment. Nevertheless, information analysis of the proteome– the entire collection of proteins that can be expressed by the lump– can 1 offer non-invasive techniques of classifying glioblastomas to aid educate treatment and 2 identify healthy protein biomarkers related to interventions to assess reaction to treatment. In this research, researchers established and examined an unique rank-based weighting technique (“RadWise”) for healthy protein includes to aid ML algorithms concentrate on the the most pertinent elements that show post-therapy outcomes. RadWise supplies a much more effective path to recognize the healthy proteins and functions that can be essential targets for treatment of these hostile, fatal tumors.
Recognizing liver cancer subtypes likely to react to immunotherapy
- Magazine : Cell Records Medicine
- Writers : Budhu, A., Pehrsson, E.C., He, A., Goyal, L., Kelley, R.K., Dang, H., Xie, C., Monge, C., Tandon, M., Ma, L., Revsine, M., Kuhlman, L., Zhang, K., Baiev, I., Lamm, R., Patel, K., Kleiner, D.E., Hewitt, S.M., Tran, B., Shetty, J., Wu, X., Zhao, Y., Shen, T.W., Choudhari, S., Kriga, Y., Ylaya, K., Warner, A.C., Edmondson, E.F., Forgues, M., Greten, T.F., Wang, X.W.
- Recap : Liver cancer is a climbing root cause of cancer cells deaths in the United States. This research checked out variant in person end results for a sort of immunotherapy using immune checkpoint inhibitors. Scientist kept in mind that specific molecular subtypes of cancer, specified by 1 the aggressiveness of cancer and 2 the microenvironment of the cancer cells, were linked to greater survival rates with immune checkpoint prevention therapy. Recognizing these molecular subtypes can aid doctors identify whether a patient’s special cancer cells is most likely to reply to this sort of intervention, indicating they can apply a lot more targeted use immunotherapy and improve chance of success.
Using algorithms to EHR data to infer maternity timing for more accurate maternal health and wellness research study
- Magazine : JAMIA, Women’s Health Scandal sheet
- Writers : Jones, S., Bradwell, K.R. *, Chan, L.E., McMurry, J.A., Olson-Chen, C., Tarleton, J., Wilkins, K.J., Qin, Q., Faherty, E.G., Lau, Y.K., Xie, C., Kao, Y.H., Liebman, M.N., Ljazouli, S. *, Mariona, F., Challa, A., Li, L., Ratcliffe, S.J., Haendel, M.A., Patel, R.C., Hill, E.L.
- Summary : There are indicators that COVID- 19 can create pregnancy issues, and expecting individuals seem at greater danger for extra serious COVID- 19 infection. Evaluation of health document (EHR) data can aid supply even more insight, however as a result of data disparities, it is frequently difficult to establish 1 maternity begin and end days and 2 gestational age of the child at birth. To aid, researchers adjusted an existing formula for identifying gestational age and pregnancy length that relies on diagnostic codes and delivery days. To boost the precision of this algorithm, the scientists layered on their own data-driven algorithms to precisely infer maternity begin, pregnancy end, and spots time frames throughout a pregnancy’s development while also resolving EHR information incongruity. This technique can be reliably made use of to make the fundamental inference of maternity timing and can be related to future pregnancy and pregnancy study on subjects such as negative maternity end results and mother’s death.
An unique method for solving EHR information quality issues for scientific experiences
- Publication : JAMIA
- Writers : Leese, P., Anand, A., Girvin, A. *, Manna, A. *, Patel, S., Yoo, Y.J., Wong, R., Haendel, M., Chute, C.G., Bennett, T., Hajagos, J., Pfaff, E., Moffitt, R.
- Summary : Professional encounter data can be an abundant source for research study, yet it typically varies significantly throughout providers, facilities, and institutions, making it difficult to uniformly evaluate. This inconsistency is magnified when multisite digital wellness document (EHR) information is networked with each other in a central data source. In this study, scientists developed an unique, generalizable method for dealing with scientific experience data for evaluation by integrating relevant experiences right into composite “macrovisits.” This approach aids manipulate and deal with EHR experience information problems in a generalizable, repeatable means, permitting scientists to extra quickly unlock the capacity of this rich data for large studies.
Improving transparency in phenotyping for Long COVID study and past
- Publication : Journal of the American Medical Informatics Association
- Writers : Pfaff, E.R., Girvin, A.T. *, Crosskey, M., Gangireddy, S., Master, H., Wei, W.Q., Kerchberger, V.E., Weiner, M., Harris, P.A., Basford, M., Lunt, C., Chute, C.G., Moffitt, R.A., Haendel, M.; N 3 C and RECOVER Consortia
- Recap : Phenotyping, the process of assessing and categorizing a microorganism’s features, can assist scientists better comprehend the differences in between individuals and teams of individuals, and to recognize specific qualities that may be connected to particular illness or conditions. Machine learning (ML) can assist obtain phenotypes from information, yet these are challenging to share and replicate due to their intricacy. Scientists in this research study developed and trained an ML-based phenotype to identify individuals very potential to have Lengthy COVID, a progressively urgent public health and wellness factor to consider, and showed applicability of this technique for other environments. This is a success tale of how clear modern technology and partnership can make phenotyping algorithms much more obtainable to a wide target market of scientists in informatics, lowering duplicated job and giving them with a tool to reach insights quicker, including for various other illness.
Browsing obstacles for multisite real life information (RWD) databases
- Publication : BMC Medical Study Method
- Authors : Sidky, H., Youthful, J.C., Girvin, A.T. *, Lee, E., Shao, Y.R., Hotaling, N., Michael, S., Wilkins, K.J., Setoguchi, S., Funk, M.J.; N 3 C Consortium
- Recap : Working with large range systematized EHR data sources such as N 3 C for research study requires specialized expertise and careful analysis of information high quality and completeness. This research checks out the procedure of examining information quality in preparation for research, concentrating on drug efficacy researches. Researchers determined several methods and best methods to better characterize essential study elements consisting of direct exposure to treatment, standard health comorbidities, and crucial outcomes of passion. As huge range, streamlined real life data sources come to be much more prevalent, this is a helpful progression in assisting scientists more effectively navigate their distinct information difficulties while unlocking essential applications for medication advancement.
What’s Next for Wellness Research at Palantir
While 2023 saw important progress, the new year brings with it brand-new possibilities, along with a seriousness to use the most recent technological advancements to the most essential health and wellness issues encountering people, areas, and the public at large. As an example, in 2023, the U.S. Government reaffirmed its dedication to combating systemic conditions such as cancer, and also launched a brand-new wellness firm, the Advanced Study Projects Firm for Health And Wellness ( ARPA-H
In addition, in 2024, Palantir is pleased to be an industry partner in the cutting-edge National AI Research Study Resource (NAIRR) pilot program , developed under the auspices of the National Scientific Research Structure (NSF) and with funding from the NIH. As component of the NAIRR pilot– whose launch was routed by the Biden Management’s Exec Order on Expert System — Palantir will certainly be collaborating with its veteran companions at the National Institutes of Health (NIH) and N 3 C to sustain research in advancing safe, safe, and trustworthy AI, as well as the application of AI to challenges in healthcare.
In 2024, we’re delighted to collaborate with companions, new and old, on concerns of critical relevance, using our learnings on information, devices, and research study to aid allow meaningful renovations in wellness results for all.
For more information about our proceeding work throughout health and life sciences, go to https://www.palantir.com/offerings/federal-health/
* Authors associated with Palantir Technologies